slow networks

The first of a short series by Welch Labs on building a complete neural network in Python. It introduces the data and the architecture of a simple network before later parts cover forward propagation, gradient descent, and backpropagation.

A guided Wim Hof breathing session of three rounds at a slow pace, building from a 30 second to a 90 second breath hold. An on-screen bubble animation helps you keep the rhythm.

Martin Gorner's Devoxx talk introduces deep learning with TensorFlow, walking through neural networks for MNIST, how to choose an architecture and how to diagnose networks that fail to train.

Andrej Karpathy builds a bigram character-level language model from scratch, introducing torch.Tensor and the framework of training, sampling and loss evaluation. It is the first step toward a GPT-style Transformer in his makemore series.

Dean Friedman's near-hour-long introduction to synthesis, covering the building blocks of sound and the controls on a synthesizer. He slowly adjusts knobs so viewers hear what each parameter does.

In this first Crust of Rust episode, Jon Gjengset live-codes an example that needs multiple explicit lifetime annotations. Along the way he covers string types and generics over a custom trait.

Mark Bittman and baker Jim Lahey of Sullivan Street Bakery demonstrate the no-knead bread recipe, where a long, slow rise does the work instead of kneading. It is a short New York Times recipe video.